Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3688 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.8249. Min Act: -0.0000

Data Index: 24540 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.6728. Min Act: -0.0000

Data Index: 1045483 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.8428. Min Act: -0.0000

Data Index: 96888 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.6401. Min Act: -0.0000

Data Index: 312946 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.5254. Min Act: -0.0000

Data Index: 946011 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.1386. Min Act: -0.0000

Data Index: 920885 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.2612. Min Act: -0.0000

Data Index: 783511 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.4062. Min Act: -0.0000

Data Index: 912013 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.3736. Min Act: -0.0000

Data Index: 151385 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.3421. Min Act: -0.0000

Data Index: 1110797 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.3028. Min Act: -0.0000

Data Index: 935110 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.4386. Min Act: -0.0000

Data Index: 519814 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.2076. Min Act: -0.0000

Data Index: 532161 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.2508. Min Act: -0.0000

Data Index: 215304 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.3406. Min Act: -0.0000

Data Index: 937537 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.3796. Min Act: -0.0000

Data Index: 740090 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.2322. Min Act: -0.0000

Data Index: 527417 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.0347. Min Act: -0.0000

Data Index: 69691 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.1251. Min Act: -0.0000

Data Index: 224844 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 2.8428. Min Range: -2.8428

Max Act: 2.2370. Min Act: -0.0000

Data Index: 837424 (C4 (Web Text))

Max Activating Token Index: 282